quant-trader

Generate structured trading signals with entry, target, stop_loss, and Kelly Criterion risk sizing.

6|Updated May 20, 2026

Search Tags:#portfolio #signals #trading #backtest #quantitative #kelly-criterion #risk-sizing

Ready to run

npx skills add https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version --skill quant-trader

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: quant-trader
Source: https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version/tree/main/quant-trader
Command: npx skills add https://github.com/vignesh2027/Claude-Agentic-Skills2.0-version --skill quant-trader

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Quickly convert raw market data into actionable, risk-aware trading signals with clearly defined entries, exits, and position sizing.

Core Features & Use Cases

Signal generation: produce buy/sell/hold signals with entry, target, stop_loss, and risk-reward.
Risk sizing: apply Kelly Criterion-based sizing and portfolio risk controls.
Backtesting & regimes: detects market regime (trending/ranging/volatile) and supports backtesting logic for strategy validation.
Output format: delivers a structured JSON signal suitable for integration into Claude or automation pipelines.

Quick Start

Supply market data to QuantTrader and receive a complete JSON trade signal with entry, target, stop_loss, risk sizing, and reasoning.

Frequently Asked Questions about quant-trader

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate structured trading signals with entry, target, and stop_loss from raw market data?▼

The system detects market regimes like trending, ranging, or volatile, and then selects the appropriate strategy to produce backtest-ready trade signals with Kelly Criterion risk sizing.

How does the Kelly Criterion apply to portfolio risk sizing for trading signals?▼

Kelly Criterion risk sizing calculates optimal position weights for your portfolio based on the generated trading signals, applying portfolio risk controls to determine appropriate capital allocation for each trade.

Can I use these quantitative trading signals for backtesting across different market regimes?▼

Yes, the signals are backtest-ready and explicitly designed to support backtesting logic by detecting trending, ranging, and volatile market regimes to validate strategy performance across varying conditions.

What is the JSON output format for trading signals and does it work with automation pipelines?▼

The output is a structured JSON signal with explicit fields for entry, target, stop_loss, and risk sizing, making it directly suitable for integration into automation pipelines or downstream systems.

Do I need historical market data to detect market regimes before generating trade signals?▼

Yes, you must supply market data as input for the deterministic workflow, which requires data ingestion to perform regime detection and strategy selection before outputting the final trade signal.